ProductizeML
  • ProductizeML
  • Introduction
    • Objectives
    • About the Course
    • Guidelines
    • Syllabus
    • After Completion
  • Machine Learning
    • Why ML, and why now
    • Supervised Learning
    • Unsupervised Learning
    • Deep Learning
    • ML Terminology
  • Data Management
    • Data Access
    • Data Collection
    • Data Curation
  • Train and Evaluate
    • Framework and Hardware
    • Training Neural Networks
    • Model Evaluation
  • Productize It
    • ML Life Cycle
    • Business Objectives
    • Data Preparation
    • Model Development
    • Train, Evaluate, and Deploy
    • A/B Testing
    • KPI Evaluation
    • PM Terminology
  • Resources
    • Readings
    • Courses
    • Videos
  • Hands-On
    • Python for Machine Learning
      • Python Installation
        • MacOS
        • Linux
Powered by GitBook
On this page

Was this helpful?

  1. Productize It

Model Development

You will learn: how to reuse existing solutions that can be adapted to your problem.

PreviousData PreparationNextTrain, Evaluate, and Deploy

Last updated 2 years ago

Was this helpful?

Before starting to develop your own models, you should probably spend some time looking if someone or any other company has faced the same problem before. If so, maybe you might consider coming up with a similar approach or requesting access to one of their services.

You can find platforms like , that curates and organizes research works and makes deep learning pretrained models available to either plugging it into your system or training it on the top of their task. You can find different categories that go from computer vision, NLP, unsupervised learning, or reinforcement learning.

Only if you cannot find related work, then it is time to do some research to try to come up with the most optimal technology set up around network architectures, tools to use, hyper-parameters values, etc.

Model Zoo
https://modelzoo.co/
Logo